Hugging Face's logo

Spaces:
fsadeek
/
gemma-fine-tuning
Running

App Files Community
gemma-fine-tuning / README.md
fsadeek's picture
fsadeek
added some features
557c6b6
preview code
|
raw
history blame contribute delete
1.43 kB

A newer version of the Gradio SDK is available: 5.49.1

Upgrade
metadata
title: Gemma Fine Tuning
emoji: 🐠
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 5.20.1
app_file: app.py
pinned: false
hf_oauth: true
hf_oauth_scopes:
  - inference-api

Gemma Fine-Tuning UI

A user-friendly web interface for fine-tuning Google's Gemma models on custom datasets.

Features

  • Easy Dataset Upload: Support for CSV, JSONL, and plain text formats
  • Intuitive Hyperparameter Configuration: Adjust learning rates, batch sizes, and other parameters with visual controls
  • Real-time Training Visualization: Monitor loss curves, evaluation metrics, and sample outputs during training
  • Flexible Model Export: Download your fine-tuned model in PyTorch, GGUF, or Safetensors formats
  • Comprehensive Documentation: Built-in guidance for fine-tuning process

Getting Started

Prerequisites

  • Python 3.8 or later
  • PyTorch 2.0 or later
  • Hugging Face account with access to Gemma models

Installation

  1. Clone this repository:

    git clone https://github.com/yourusername/gemma-fine-tuning.git
cd gemma-fine-tuning

  2. Install the required packages:

    pip install -r requirements.txt

  3. Launch the application:

    python app.py

  4. Open your browser and navigate to http://localhost:7860

Usage Guide

1. Dataset Preparation

Prepare your dataset in one of the supported formats:

CSV format: